| { | |
| "best_metric": 0.3735887110233307, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 1.1822660098522166, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015763546798029555, | |
| "grad_norm": 29.17995262145996, | |
| "learning_rate": 2e-05, | |
| "loss": 13.3509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015763546798029555, | |
| "eval_loss": 13.427430152893066, | |
| "eval_runtime": 0.7017, | |
| "eval_samples_per_second": 71.258, | |
| "eval_steps_per_second": 18.527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03152709359605911, | |
| "grad_norm": 28.460174560546875, | |
| "learning_rate": 4e-05, | |
| "loss": 12.8886, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04729064039408867, | |
| "grad_norm": 27.8137264251709, | |
| "learning_rate": 6e-05, | |
| "loss": 12.7057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06305418719211822, | |
| "grad_norm": 26.662076950073242, | |
| "learning_rate": 8e-05, | |
| "loss": 11.5203, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 28.166336059570312, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09458128078817735, | |
| "grad_norm": 27.162477493286133, | |
| "learning_rate": 9.997539658034168e-05, | |
| "loss": 6.8103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 22.779897689819336, | |
| "learning_rate": 9.990161322484486e-05, | |
| "loss": 4.7953, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12610837438423644, | |
| "grad_norm": 31.25025749206543, | |
| "learning_rate": 9.977873061452552e-05, | |
| "loss": 3.5934, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14187192118226602, | |
| "grad_norm": 32.73939895629883, | |
| "learning_rate": 9.96068831197139e-05, | |
| "loss": 2.0744, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 22.30132293701172, | |
| "learning_rate": 9.938625865312251e-05, | |
| "loss": 0.9963, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17339901477832512, | |
| "grad_norm": 23.55769920349121, | |
| "learning_rate": 9.911709846436641e-05, | |
| "loss": 0.7853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1891625615763547, | |
| "grad_norm": 12.216867446899414, | |
| "learning_rate": 9.879969687616027e-05, | |
| "loss": 0.6935, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20492610837438424, | |
| "grad_norm": 13.3597993850708, | |
| "learning_rate": 9.84344009624807e-05, | |
| "loss": 0.7613, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 9.345667839050293, | |
| "learning_rate": 9.80216101690461e-05, | |
| "loss": 0.5759, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "grad_norm": 11.192370414733887, | |
| "learning_rate": 9.756177587652856e-05, | |
| "loss": 0.6503, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2522167487684729, | |
| "grad_norm": 11.622135162353516, | |
| "learning_rate": 9.705540090697575e-05, | |
| "loss": 0.6265, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26798029556650244, | |
| "grad_norm": 13.78838062286377, | |
| "learning_rate": 9.650303897398232e-05, | |
| "loss": 0.5981, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.28374384236453204, | |
| "grad_norm": 7.175749778747559, | |
| "learning_rate": 9.590529407721231e-05, | |
| "loss": 0.5388, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2995073891625616, | |
| "grad_norm": 12.73121452331543, | |
| "learning_rate": 9.526281984193436e-05, | |
| "loss": 0.6199, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.31527093596059114, | |
| "grad_norm": 13.318937301635742, | |
| "learning_rate": 9.4576318804292e-05, | |
| "loss": 0.561, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3310344827586207, | |
| "grad_norm": 1.523805022239685, | |
| "learning_rate": 9.384654164309083e-05, | |
| "loss": 0.5285, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34679802955665023, | |
| "grad_norm": 27.318439483642578, | |
| "learning_rate": 9.30742863589421e-05, | |
| "loss": 0.7602, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3625615763546798, | |
| "grad_norm": 27.310163497924805, | |
| "learning_rate": 9.226039740166091e-05, | |
| "loss": 0.8761, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3783251231527094, | |
| "grad_norm": 19.47849464416504, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 0.6216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 2.0372307300567627, | |
| "learning_rate": 9.051132292283771e-05, | |
| "loss": 0.4954, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "eval_loss": 0.6996614336967468, | |
| "eval_runtime": 0.7017, | |
| "eval_samples_per_second": 71.253, | |
| "eval_steps_per_second": 18.526, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4098522167487685, | |
| "grad_norm": 25.538625717163086, | |
| "learning_rate": 8.957804998855866e-05, | |
| "loss": 0.8154, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.42561576354679803, | |
| "grad_norm": 25.62391471862793, | |
| "learning_rate": 8.860696646428693e-05, | |
| "loss": 0.8749, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4413793103448276, | |
| "grad_norm": 21.496841430664062, | |
| "learning_rate": 8.759913421559902e-05, | |
| "loss": 0.7513, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 6.727818489074707, | |
| "learning_rate": 8.655565529226198e-05, | |
| "loss": 0.5105, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4729064039408867, | |
| "grad_norm": 10.45919418334961, | |
| "learning_rate": 8.547767072315835e-05, | |
| "loss": 0.5997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4886699507389163, | |
| "grad_norm": 12.25587272644043, | |
| "learning_rate": 8.436635926858759e-05, | |
| "loss": 0.665, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5044334975369458, | |
| "grad_norm": 12.651376724243164, | |
| "learning_rate": 8.322293613130917e-05, | |
| "loss": 0.6593, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5201970443349754, | |
| "grad_norm": 6.981288909912109, | |
| "learning_rate": 8.204865162773613e-05, | |
| "loss": 0.5065, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5359605911330049, | |
| "grad_norm": 11.137550354003906, | |
| "learning_rate": 8.084478982073247e-05, | |
| "loss": 0.5894, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 14.628920555114746, | |
| "learning_rate": 7.961266711550922e-05, | |
| "loss": 0.6922, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5674876847290641, | |
| "grad_norm": 9.037491798400879, | |
| "learning_rate": 7.835363082015468e-05, | |
| "loss": 0.5246, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5832512315270936, | |
| "grad_norm": 7.97292423248291, | |
| "learning_rate": 7.706905767237288e-05, | |
| "loss": 0.4837, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5990147783251232, | |
| "grad_norm": 2.1145670413970947, | |
| "learning_rate": 7.576035233404096e-05, | |
| "loss": 0.5613, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6147783251231527, | |
| "grad_norm": 9.712841033935547, | |
| "learning_rate": 7.442894585523218e-05, | |
| "loss": 0.6461, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6305418719211823, | |
| "grad_norm": 15.202656745910645, | |
| "learning_rate": 7.307629410938363e-05, | |
| "loss": 0.731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6463054187192119, | |
| "grad_norm": 10.122875213623047, | |
| "learning_rate": 7.170387620131993e-05, | |
| "loss": 0.6261, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6620689655172414, | |
| "grad_norm": 5.730849742889404, | |
| "learning_rate": 7.031319284987394e-05, | |
| "loss": 0.5371, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.677832512315271, | |
| "grad_norm": 1.8030896186828613, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 0.5414, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6935960591133005, | |
| "grad_norm": 4.4432692527771, | |
| "learning_rate": 6.7483130894283e-05, | |
| "loss": 0.5234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7093596059113301, | |
| "grad_norm": 4.838330268859863, | |
| "learning_rate": 6.604684692133597e-05, | |
| "loss": 0.5282, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7251231527093596, | |
| "grad_norm": 4.681862831115723, | |
| "learning_rate": 6.459848338346861e-05, | |
| "loss": 0.5099, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7408866995073892, | |
| "grad_norm": 1.7629047632217407, | |
| "learning_rate": 6.313962404494496e-05, | |
| "loss": 0.5132, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7566502463054188, | |
| "grad_norm": 6.828063011169434, | |
| "learning_rate": 6.167186414703289e-05, | |
| "loss": 0.5072, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7724137931034483, | |
| "grad_norm": 12.11754035949707, | |
| "learning_rate": 6.019680866363139e-05, | |
| "loss": 0.5966, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "grad_norm": 11.806983947753906, | |
| "learning_rate": 5.8716070546254966e-05, | |
| "loss": 0.5767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "eval_loss": 0.5248658061027527, | |
| "eval_runtime": 0.7022, | |
| "eval_samples_per_second": 71.202, | |
| "eval_steps_per_second": 18.513, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8039408866995074, | |
| "grad_norm": 7.980965614318848, | |
| "learning_rate": 5.7231268960295e-05, | |
| "loss": 0.5778, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.819704433497537, | |
| "grad_norm": 4.428957462310791, | |
| "learning_rate": 5.574402751448614e-05, | |
| "loss": 0.5315, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8354679802955665, | |
| "grad_norm": 4.525695323944092, | |
| "learning_rate": 5.425597248551387e-05, | |
| "loss": 0.4983, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8512315270935961, | |
| "grad_norm": 1.8734763860702515, | |
| "learning_rate": 5.2768731039705e-05, | |
| "loss": 0.4634, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8669950738916257, | |
| "grad_norm": 3.463655948638916, | |
| "learning_rate": 5.128392945374505e-05, | |
| "loss": 0.4803, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8827586206896552, | |
| "grad_norm": 3.0169169902801514, | |
| "learning_rate": 4.980319133636863e-05, | |
| "loss": 0.4406, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8985221674876848, | |
| "grad_norm": 3.7181005477905273, | |
| "learning_rate": 4.83281358529671e-05, | |
| "loss": 0.5167, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 2.4602622985839844, | |
| "learning_rate": 4.686037595505507e-05, | |
| "loss": 0.4639, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9300492610837439, | |
| "grad_norm": 3.199212074279785, | |
| "learning_rate": 4.54015166165314e-05, | |
| "loss": 0.4315, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9458128078817734, | |
| "grad_norm": 4.430737495422363, | |
| "learning_rate": 4.395315307866405e-05, | |
| "loss": 0.5223, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.961576354679803, | |
| "grad_norm": 7.746757507324219, | |
| "learning_rate": 4.2516869105717004e-05, | |
| "loss": 0.4648, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9773399014778326, | |
| "grad_norm": 7.860967636108398, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 0.4422, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.993103448275862, | |
| "grad_norm": 1.5262166261672974, | |
| "learning_rate": 3.968680715012606e-05, | |
| "loss": 0.4396, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0088669950738915, | |
| "grad_norm": 12.424480438232422, | |
| "learning_rate": 3.829612379868006e-05, | |
| "loss": 0.7924, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0246305418719213, | |
| "grad_norm": 7.300468444824219, | |
| "learning_rate": 3.692370589061639e-05, | |
| "loss": 0.5098, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0403940886699508, | |
| "grad_norm": 6.1646599769592285, | |
| "learning_rate": 3.557105414476782e-05, | |
| "loss": 0.4455, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0561576354679802, | |
| "grad_norm": 3.547170639038086, | |
| "learning_rate": 3.423964766595906e-05, | |
| "loss": 0.4332, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.07192118226601, | |
| "grad_norm": 2.7341320514678955, | |
| "learning_rate": 3.293094232762715e-05, | |
| "loss": 0.3857, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0876847290640395, | |
| "grad_norm": 2.705845355987549, | |
| "learning_rate": 3.164636917984534e-05, | |
| "loss": 0.4454, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 5.191798210144043, | |
| "learning_rate": 3.0387332884490805e-05, | |
| "loss": 0.4356, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1192118226600984, | |
| "grad_norm": 1.7099392414093018, | |
| "learning_rate": 2.9155210179267546e-05, | |
| "loss": 0.4155, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1349753694581282, | |
| "grad_norm": 4.040687561035156, | |
| "learning_rate": 2.7951348372263875e-05, | |
| "loss": 0.4195, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1507389162561577, | |
| "grad_norm": 5.240128517150879, | |
| "learning_rate": 2.677706386869083e-05, | |
| "loss": 0.4251, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1665024630541871, | |
| "grad_norm": 4.154675483703613, | |
| "learning_rate": 2.5633640731412412e-05, | |
| "loss": 0.4514, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.1822660098522166, | |
| "grad_norm": 2.458857536315918, | |
| "learning_rate": 2.4522329276841663e-05, | |
| "loss": 0.3418, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1822660098522166, | |
| "eval_loss": 0.3735887110233307, | |
| "eval_runtime": 0.7016, | |
| "eval_samples_per_second": 71.267, | |
| "eval_steps_per_second": 18.53, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.384195670245376e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |